SP 537 update winnowing and file filters

CHANGELOG.md

@@ -11,6 +11,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Upcoming changes...
 
+## [0.7.1] - 2024-04-12
+### Changed
+- Update file and winnowing filters
+- Remove filter for '.whl' file extensions
+- Added dir extension filter
+
 ## [0.7.0] - 2024-04-04
 ### Added
 - Add HPSM support
@@ -79,3 +85,4 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 [0.6.0]: https://github.com/scanoss/scanoss.java/compare/v0.5.5...v0.6.0
 [0.6.1]: https://github.com/scanoss/scanoss.java/compare/v0.6.0...v0.6.1
 [0.7.0]: https://github.com/scanoss/scanoss.java/compare/v0.6.1...v0.7.0
+[0.7.1]: https://github.com/scanoss/scanoss.java/compare/v0.7.0...v0.7.1

pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.scanoss</groupId>
     <artifactId>scanoss</artifactId>
-    <version>0.7.0</version>
+    <version>0.7.1</version>
     <packaging>jar</packaging>
     <name>scanoss.java</name>
     <url>https://github.com/scanoss/scanoss.java</url>

src/main/java/com/scanoss/Scanner.java

@@ -156,19 +156,29 @@ public String wfpFile(@NonNull String filename) throws ScannerException, Winnowi
      * @return <code>true</code> if the folder should be skipped, <code>false</code> otherwise
      */
     private Boolean filterFolder(String name) {
+        String nameLower =  name.toLowerCase();
         if (!hiddenFilesFolders && name.startsWith(".") && !name.equals(".")) {
             log.trace("Skipping hidden folder: {}", name);
             return true;
         }
+        boolean ignore = false;
         if (!allFolders) { // skip this check if all folders is selected
             for (String ending : ScanossConstants.FILTERED_DIRS) {
-                if (name.endsWith(ending)) {
+                if (nameLower.endsWith(ending)) {
                     log.trace("Skipping folder due to ending: {} - {}", name, ending);
-                    return true;
+                    ignore = true;
+                }
+            }
+            if(!ignore){
+                for (String ending : ScanossConstants.FILTERED_DIR_EXT) {
+                    if (nameLower.endsWith(ending)) {
+                        log.trace("Skipping folder due to ending: {} - {}", name, ending);
+                        ignore = true;
+                    }
                 }
             }
         }
-        return false;
+        return ignore;
     }
 
     /**

src/main/java/com/scanoss/ScanossConstants.java

@@ -36,7 +36,7 @@ public class ScanossConstants {
             ".o", ".a", ".so", ".obj", ".dll", ".lib", ".out", ".app", ".bin",
             ".lst", ".dat", ".json", ".htm", ".html", ".xml", ".md", ".txt",
             ".doc", ".docx", ".xls", ".xlsx", ".ppt", ".pptx", ".odt", ".ods", ".odp", ".pages", ".key", ".numbers",
-            ".pdf", ".min.js", ".mf", ".sum", ".woff", ".woff2"
+            ".pdf", ".min.js", ".mf", ".sum", ".woff", ".woff2", ".xsd", ".pom", ".whl"
     );
 
     // Folders to skip
@@ -45,6 +45,10 @@ public class ScanossConstants {
             "__pypackages__", "target"
     );
 
+    // Folder endings to skip
+    static final List<String> FILTERED_DIR_EXT = List.of(".egg-info");
+
+
     // File extensions to skip
     static final List<String> FILTERED_EXTENSIONS = Arrays.asList(
             ".1", ".2", ".3", ".4", ".5", ".6", ".7", ".8", ".9", ".ac", ".adoc", ".am",
@@ -59,7 +63,7 @@ public class ScanossConstants {
             ".po", ".ppt", ".prefs", ".properties", ".pyc", ".qdoc", ".result", ".rgb",
             ".rst", ".scss", ".sha", ".sha1", ".sha2", ".sha256", ".sln", ".spec", ".sql",
             ".sub", ".svg", ".svn-base", ".tab", ".template", ".test", ".tex", ".tiff",
-            ".toml", ".ttf", ".txt", ".utf-8", ".vim", ".wav", ".whl", ".woff", ".woff2", ".xht",
+            ".toml", ".ttf", ".txt", ".utf-8", ".vim", ".wav", ".woff", ".woff2", ".xht",
             ".xhtml", ".xls", ".xlsx", ".xml", ".xpm", ".xsd", ".xul", ".yaml", ".yml", ".wfp",
             ".editorconfig", ".dotcover", ".pid", ".lcov", ".egg", ".manifest", ".cache", ".coverage", ".cover",
             ".gem", ".lst", ".pickle", ".pdb", ".gml", ".pot", ".plt",

src/test/java/com/scanoss/TestScanner.java

@@ -242,12 +242,30 @@ public void TestScannerScanFileListNegative() {
         log.info("Finished {} -->", methodName);
     }
 
-        @Test
+    @Test
     public void TestScannerTemplate() {
         String methodName = new Object() {
         }.getClass().getEnclosingMethod().getName();
         log.info("<-- Starting {}", methodName);
 
         log.info("Finished {} -->", methodName);
     }
+
+    @Test
+    public void TestIgnoreFolderExtension() {
+        String methodName = new Object() {
+        }.getClass().getEnclosingMethod().getName();
+        log.info("<-- Starting {}", methodName);
+
+        Scanner scanner = Scanner.builder().build();
+        String folder = "testing/data/test-folder-ignore";
+        List<String> results = scanner.scanFolder(folder);
+        log.info("Received {} results", results.size());
+        assertFalse("Scan results should be empty", results.isEmpty());
+        assertEquals("Results should be one", results.size() , 1);
+
+        log.info("Finished {} -->", methodName);
+    }
+
+
 }